Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System

Yan, Rui; Song, Yiping; Wu, Hua

doi:10.1145/2911451.2911542

Cited by 316 publications

(179 citation statements)

References 30 publications

Supporting

Mentioning

179

Contrasting

Order By: Relevance

“…While it may do so, this framing may be far too narrow, as Li (2016)'s presentation suggests. The great strength of Neural IR may lie in enabling a new generation of search scenarios and modalities, such as searching via conversational agents (Yan et al 2016), multi-modal retrieval (Ma et al 2015a, b), knowledge-based search IR (Nguyen et al 2016), or synthesis of relevant material (Lioma et al 2016). It may also be that Neural IR will provide greater traction for other future search scenarios not yet considered.…”

Section: Resultsmentioning

confidence: 99%

“…Learn to match An automatic conversation response system called Deep Learning-toRespond (DL2R) is proposed by Yan et al (2016). They train and test on 10 million posting-reply pairs of human conversation web data from various sources, including microblog websites, forums, Community Question Answering (CQA) bases, etc.…”

Section: Learnmentioning

confidence: 99%

“…However, rather than take the whole text of a document, they extract a context window of AEn terms around every query term occurrence. Yan et al (2016) use a bidirectional LSTM followed by a CNN to model the original query, reformulated query, candidate reply, and antecedent post in their human-computer conversation system. Wang and Nyberg (2015) use a stacked bidirectional LSTM to sequentially read words from both question and answer sentences, calculating relevance scores for answer sentence selection through mean pooling across all time steps.…”

Section: How To Choose the Appropriate Category Of Learn?mentioning

confidence: 99%

“…Wang and Nyberg (2015) use a stacked bidirectional LSTM to sequentially read words from both question and answer sentences, calculating relevance scores for answer sentence selection through mean pooling across all time steps. Yan et al (2016) match sentences by concatenating their vector representations and feeding them into a multi-layer fully-connected neural network, matching a query with the posting and reply in a human computer conversation system. Xia et al (2016) propose a neural tensor network (NTN) approach to model document novelty.…”

Section: How To Choose the Appropriate Category Of Learn?mentioning

confidence: 99%

See 3 more Smart Citations

Neural information retrieval: at the end of the early years

et al. 2017

View full text Add to dashboard Cite

A recent ''third wave'' of neural network (NN) approaches now delivers state-ofthe-art performance in many machine learning tasks, spanning speech recognition, computer vision, and natural language processing. Because these modern NNs often comprise multiple interconnected layers, work in this area is often referred to as deep learning. Recent years have witnessed an explosive growth of research into NN-based approaches to information retrieval (IR). A significant body of work has now been created. In this paper,

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Learnmentioning

confidence: 99%

Section: How To Choose the Appropriate Category Of Learn?mentioning

confidence: 99%

Section: How To Choose the Appropriate Category Of Learn?mentioning

confidence: 99%

See 2 more Smart Citations

Neural information retrieval: at the end of the early years

et al. 2017

View full text Add to dashboard Cite

show abstract

“…One critical issue for open domain conversation is to produce a reasonable response. Responding to this challenge, two promising solutions have been proposed: 1) retrieval-based model which selects a response from a large corpus (Ji et al, 2014;Yan et al, 2016;. 2) generation-based model which directly generates the next utterance (Wen et al, 2015a;Wen et al, 2015b).…”

Section: Conversation Systemmentioning

confidence: 99%

Multi-view Response Selection for Human-Computer Conversation

Zhou¹,

Dong²,

Wu³

et al. 2016

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

Self Cite

208

171

View full text Add to dashboard Cite

In this paper, we study the task of response selection for multi-turn human-computer conversation. Previous approaches take word as a unit and view context and response as sequences of words. This kind of approaches do not explicitly take each utterance as a unit, therefore it is difficult to catch utterancelevel discourse information and dependencies. In this paper, we propose a multi-view response selection model that integrates information from two different views, i.e., word sequence view and utterance sequence view. We jointly model the two views via deep neural networks. Experimental results on a public corpus for context-sensitive response selection demonstrate the effectiveness of the proposed multi-view model, which significantly outperforms other single-view baselines.

show abstract

Emotion Analysis for the Upcoming Response in Open-Domain Human-Computer Conversation

Zhang

2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Learning to Respond with Deep Neural Networks for Retrieval-Based Human-Computer Conversation System

Cited by 316 publications

References 30 publications

Neural information retrieval: at the end of the early years

Neural information retrieval: at the end of the early years

Multi-view Response Selection for Human-Computer Conversation

Emotion Analysis for the Upcoming Response in Open-Domain Human-Computer Conversation

Contact Info

Product

Resources

About